Customer-obsessed science
Research areas
-
January 14, 2025Key exchange protocols and authentication mechanisms solve distinct problems and must be integrated in a secure communication system.
-
December 24, 2024
-
December 24, 2024
-
-
Featured news
-
2024Multimodal Large Language Models (MLLMs) excel at synthesizing key information from diverse sources. However, generating accurate and faithful multimodal summaries is challenging, primarily due to the lack of appropriate multimodal datasets for fine-tuning that meaningfully integrate textual and visual modalities. To address this gap, we present a new dataset specifically designed for image-text multimodal
-
2024End-to-end neural diarization (EEND) models offer significant improvements over traditional embedding-based Speaker Diarization (SD) approaches but falls short on generalizing to long-form audio with large number of speakers. EEND-vector-clustering method mitigates this by combining local EEND with global clustering of speaker embeddings from local windows, but this requires an additional speaker embedding
-
SAT 20242024Quantum Computing (QC) is a new computational paradigm that promises significant speedup over classical computing in various domains. However, near-term QC faces numerous challenges, including limited qubit connectivity and noisy quantum operations. To address the qubit connectivity constraint, circuit mapping is required for executing quantum circuits on quantum computers. This process involves performing
-
2024Speaker Diarization (SD) systems are typically audio-based and operate independently of the ASR system in traditional speech transcription pipelines and can have speaker errors due to SD and/or ASR reconciliation, especially around speaker turns and regions of speech overlap. To reduce these errors, a Lexical Speaker Error Correction (LSEC), in which an external language model provides lexical information
-
NAACL 2024 Workshop on TrustNLP2024Large language models incorporate world knowledge and present breakthrough performances on zero-shot learning. However, these models capture societal bias (e.g., gender or racial bias) due to bias during the training process which raises ethical concerns or can even be potentially harmful. The issue is more pronounced in multi-modal settings, such as image captioning, as images can also add onto biases
Academia
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all